Retrieval Augmented Generation Apps Learnings

RAG with Apache Airflow, LlamaIndex, and Qdrant

A content navigator powered by GPT-3.5-Turbo to explore multiple documents uploaded using Streamlit UI. It uses `Document Array Memory` for small and `Pinecone` for large document pools and delivers concise, referenced search results.

Developed an Azure OpenAI-based RAG email marketing platform with a Streamlit frontend and FIASS vector database for similarity search. The platform processes multiple input formats, including CSV, PDF, text, and PPT, and incorporates product descriptions and sales data to generate creative content and matplotlib graphs based on the input data.

In this project, I leveraged the RAG (Retrieval-Augmented Generation) concept to build a complete chat pipeline from scratch. Notably, I did not rely on any online RAG frameworks (e.g., Ollama).

random and continuous choose your own adventure

Detailed description given in the README

DocQ is a fast, open-source Q&A bot that finds answers from your PDFs in seconds. Just upload your documents and ask questions, no more scrolling!

This is a minimal implementation of the multi-source RAG chatbot

A basic RAG that allows you to upload code files, process them, and query them using Ollama models

Q-RAG: Improving Educational QA with Query-to-query Retrieval and Feedback Loop

RAG (Retrieval-Augmented Generation) to answer questions based on your PDF documents with accurate contextual responses.

A FastAPI-based Retrieval-Augmented Generation (RAG) chatbot with audio upload, Whisper transcription, FAISS vector search, and GPT-powered responses.

A practical POC demonstrating how to build and run a local MCP server with Retrieval-Augmented Generation (RAG) for semantic search over internal documentation. Leverages Node.js, TypeScript, Hugging Face embeddings, and an in-memory vector store to enable fast, context-aware answers in tools like Cursor.

Thesis about RAG

Advanced RAG pipeline with UI, Local + Colab

Production-ready RAG system starter kit with local LLM inference, hybrid search, and intelligent document processing - deploy AI that learns from your knowledge base in minutes.

🔍 Build a production-ready RAG system for multi-modal search across text, images, audio, and video using LangChain and LLMs for effective knowledge retrieval.

Dive into LangChain, a powerful platform that lets you interact with your data like never before. This guide offers insights on its unique capabilities, helping you tap into your data in conversational ways.